Knowledge catalogue
arXiv:2605.12178v1 Announce Type: cross Abstract: World models enable agents to anticipate the effects of their actions by internalizing environment dynamics. In enterprise systems, however, these dyn
arXiv:2603.09678v2 Announce Type: replace-cross Abstract: Large language models achieve near-ceiling performance on code generation benchmarks, yet most of the programming languages used by popular be
arXiv:2605.12225v1 Announce Type: new Abstract: Understanding the internal machinations of deep Transformer-based NLP models is more crucial than ever as these models see widespread use in various dom
arXiv:2501.02955v2 Announce Type: replace Abstract: In recent years, vision language models (VLMs) have made significant advancements in video understanding. However, a crucial capability - fine-grain
arXiv:2605.12460v1 Announce Type: cross Abstract: The continued improvements in language model capability have unlocked their widespread use as drivers of autonomous agents, for example in coding or c
arXiv:2605.12241v1 Announce Type: cross Abstract: Specialized foundation models are beginning to emerge in various medical subdomains, but pretraining methodologies and parametric scaling with the siz
arXiv:2605.11845v1 Announce Type: new Abstract: Language models are increasingly used in settings where outputs must satisfy user-specified randomness constraints, yet their generation probabilities a
arXiv:2605.11483v1 Announce Type: new Abstract: While large language models excel at factual adaptation, their ability to internalize nuanced philosophical frameworks under severe data constraints rem
arXiv:2605.12090v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have achieved strong semantic generalization for embodied policy learning, yet they learn reactive observation-to-
arXiv:2605.09011v1 Announce Type: cross Abstract: We investigate the geometry of predictive information across the layers of large language models (LLMs). We repurpose representation lenses-learned af
arXiv:2605.08539v1 Announce Type: cross Abstract: Inductive biases influence the behavior and performance of sequential models. In this work, we study an underexplored inductive bias in sequential mod
arXiv:2602.03783v2 Announce Type: replace-cross Abstract: Modern AI agents such as large language models are trained on diverse tasks -- translation, code generation, mathematical reasoning, and text
arXiv:2605.09042v1 Announce Type: new Abstract: Evaluating pragmatic reasoning in large language models (LLMs) remains challenging because model behavior can vary depending on evaluation methods. Prev
arXiv:2605.10141v1 Announce Type: new Abstract: Recent neural theorem provers use reinforcement learning with verifiable rewards (RLVR), where proof assistants provide binary correctness signals. Whil
arXiv:2411.04077v2 Announce Type: replace Abstract: By leveraging both texts and images, large vision language models (LVLMs) have shown significant progress in various multi-modal tasks. Nevertheless
arXiv:2605.08279v1 Announce Type: cross Abstract: Learning predictive world models from visual observations is a core problem in embodied AI, with applications to model-based reinforcement learning an
arXiv:2605.10806v1 Announce Type: cross Abstract: Generative world models are increasingly used for video generation, where learned simulators are expected to capture the physical rules that govern re
arXiv:2605.09504v1 Announce Type: cross Abstract: We present swarm-attack, an open-source adversarial testing framework in which multiple lightweight LLM agents coordinate through shared memory, paral
arXiv:2605.09630v1 Announce Type: new Abstract: Tokenizer-free language models eliminate the tokenizer step of the language modeling pipeline by operating directly on bytes; patch-based variants furth
arXiv:2605.09224v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) have been used widely to decompose and interpret neural network activations, especially those of transformer language models.
arXiv:2602.03916v3 Announce Type: replace-cross Abstract: Spatial reasoning is a fundamental aspect of human cognition, yet it remains a major challenge for contemporary vision-language models (VLMs).
arXiv:2605.09742v1 Announce Type: cross Abstract: Selective state space models (SSMs), such as Mamba, achieve strong per-token expressivity by making the time discretization step Tilde{Delta} a learne
arXiv:2605.09670v1 Announce Type: cross Abstract: Teleoperation systems are fundamentally limited by communication latency, which degrades situational awareness and control performance. Predictive dis
arXiv:2601.22478v3 Announce Type: replace Abstract: Group Relative Policy Optimization (GRPO) has become the dominant method for reinforcement learning with verifiable rewards in large language models
arXiv:2603.18113v2 Announce Type: replace-cross Abstract: As large language models (LLMs) increasingly shape content generation, interaction, and decision-making across the Web, aligning them with hum
arXiv:2605.10485v1 Announce Type: new Abstract: Precise spatial reasoning is fundamental to robotic manipulation, yet the visual backbones of current vision-language-action (VLA) models are predominan
arXiv:2605.08842v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) language models organize knowledge into explicitly routed expert modules, making expert-level representations traceable and ana
arXiv:2605.07193v1 Announce Type: new Abstract: Generative modeling over discrete structures underpins applications across deep learning, from biological sequence design and code generation to large l
arXiv:2605.07544v1 Announce Type: new Abstract: When you read a paper about a new Vision-Language Model today, it can be easy to forget how strange this idea would have sounded not so long ago. Teachi
arXiv:2605.07433v1 Announce Type: cross Abstract: Qualitative models provide crucial instruments for modelling complex biological systems. While advances in automated reasoning and symbolic encodings
arXiv:2509.26524v3 Announce Type: replace-cross Abstract: In federated learning (FL), local personalization of models has received significant attention, yet personalized fine-tuning of foundation mod
arXiv:2605.07237v1 Announce Type: new Abstract: Tool-integrated reasoning (TIR) has emerged as a dominant paradigm for mathematical problem solving in language models, combining natural language (NL)
arXiv:2605.07990v1 Announce Type: cross Abstract: When a tool-calling agent picks the wrong tool, the failure is invisible until execution: the email gets sent, the meeting gets missed. Probing 12 ins
arXiv:2605.06815v1 Announce Type: new Abstract: The pursuit of artificial general intelligence necessitates robust methods for evaluating the cognitive capabilities of models beyond narrow task perfor
arXiv:2605.07260v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) language models route each token to a small subset of experts, but whether the routes selected by a trained top-k router are
arXiv:2605.04171v1 Announce Type: new Abstract: Large Language models (LLMs) show extraordinary abilities, but they are still prone to hallucinations, especially when we use them for generating Academ
arXiv:2605.03667v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved remarkable capabilities, but their immense computational demands during training remain a critical bottleneck
arXiv:2605.03050v1 Announce Type: new Abstract: Millions of users turn to AI models for their information needs. It is conceivable that a large number of user queries contain assumptions that may be f
🧠 Introducing NeuralBench: a unified, open-source framework to benchmark NeuroAI models. v1.0: 36 EEG tasks, 94 datasets, task-specific + foundation models. MEG/fMRI ready. MIT-licensed, FAIR's Brain
arXiv:2605.02962v1 Announce Type: new Abstract: Deep learning models for drug--target interaction (DTI) prediction often achieve strong benchmark performance without necessarily relying on mechanistic
arXiv:2605.03821v1 Announce Type: new Abstract: Existing robot video world models are typically trained with low-level objectives such as reconstruction and perceptual similarity, which are poorly ali
arXiv:2506.09082v5 Announce Type: replace Abstract: The rise of vision foundation models (VFMs) calls for systematic evaluation. A common approach pairs VFMs with large language models (LLMs) as gener
arXiv:2605.01373v1 Announce Type: new Abstract: The iterative denoising paradigm of Diffusion Large Language Models (DLMs) endows them with a distinct advantage in global context modeling. However, cu
arXiv:2603.09625v2 Announce Type: replace Abstract: Deep learning models benefit from increasing data diversity and volume, motivating synthetic data augmentation to improve existing datasets. However
arXiv:2512.21985v2 Announce Type: replace Abstract: In high-stakes domains, small task-specific vision models are crucial due to their low computational requirements and the availability of numerous m
arXiv:2605.02881v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models aim to provide a single generalist controller for robots, but today's systems fall short on the criteria that matter
Open models should compete on cost and specialization, not frontier benchmarks @natolambert puts it well: the right benchmark is savings in compute and time, especially for repetitive agent tasks deep
arXiv:2511.21086v2 Announce Type: replace Abstract: Large language models must satisfy hard orthographic constraints during controlled text generation, yet systematic cross-family evaluation remains l
arXiv:2605.00161v1 Announce Type: new Abstract: Diffusion language models (DLMs) are an attractive alternative to autoregressive models because they promise sublinear-time, parallel generation, yet pr
arXiv:2605.00421v1 Announce Type: new Abstract: Large language models (LLMs) show promise in radiology but their deployment is limited by computational requirements that preclude use in resource-const
arXiv:2603.17837v3 Announce Type: replace-cross Abstract: During conversational interactions, humans subconsciously engage in concurrent thinking while listening to a speaker. Although this internal c
arXiv:2604.27043v1 Announce Type: new Abstract: Today's AI assistants such as OpenClaw are designed to handle context effectively, making context learning an increasingly important capability for mode
arXiv:2512.14067v2 Announce Type: replace-cross Abstract: Diffusion language models (dLMs) have emerged as a promising paradigm that enables parallel, non-autoregressive generation, but their learning
arXiv:2604.26478v1 Announce Type: new Abstract: Hyperspectral imaging (HSI) semantic segmentation typically relies on in-domain training, but limited data availability often restricts model performanc
Goblin and related magical mentions were overrewarded in training, and the behavior was reinforced over successive models. We removed the goblin-affine reward signal for future models, and filtered tr
arXiv:2604.25934v1 Announce Type: cross Abstract: The deployment of large language models (LLMs) as interactive agents has exposed a category of behavioral failure that prevailing terminology, princip
OpenAI: OpenAI says its models, starting with GPT-5.1, “increasingly mentioned goblins, gremlins, and other creatures”, leading to prompt instructions to mitigate it — Starting with GPT-5.1, our model
arXiv:2505.24867v2 Announce Type: replace-cross Abstract: Recent advances in vision-language models (VLMs) have made impressive strides in understanding spatio-temporal relationships in videos. Howeve
arXiv:2604.25072v1 Announce Type: new Abstract: Unified Multimodal Models (uMMs) aim to support both visual understanding and visual generation within a shared representation. However, existing evalua
arXiv:2410.06723v2 Announce Type: replace-cross Abstract: Pathology foundation models (PFMs) have emerged as powerful pretrained encoders for computational pathology, but their robustness under clinic